Controller 窗口可能会过早关闭，或在 worker 运行时浪费上下文。此技能会安排低频、ETA 感知的检查，并等待明确的终止状态。

Important project context is easily lost between sessions. This skill stores it in structured files and helps retrieve it later with PARA and qmd.

Creating a new agent requires consistent configuration, a clear role charter, and the correct approval process. This skill guides Paperclip users through discovery, drafting, review, submission, and approval follow-up.

Plans often fail when tasks lack owners, dependencies, or clear starting conditions. This skill turns accepted Paperclip plans into a verified task graph that supports focused and parallel execution.

Managing an AI-agent company can require many API calls and scattered operational checks. This skill turns board requests into structured Paperclip workflows for onboarding, approvals, monitoring, and review.

Teams need a consistent way to coordinate agent work, approvals, and task progress. This skill guides Paperclip API workflows for assignments, updates, routines, and deliverables.

创建有用的 AI 技能需要的不只是通用说明。此技能会指导 Claude、Codex 和 Claude Code 在起草技能之前，先研究经过验证的专家方法。

手动期货订单流程容易出错且速度较慢。此技能通过结构化检查、确认和结果摘要来指导 Gate MCP 操作。

Event hosts need accurate beverage quantities without hidden consumption assumptions. This skill converts approved inputs into reviewable servings, packages, inventory gaps, and ingredient totals.

Recorded bottle lists become unreliable after purchases, moves, and regular use. This skill compares both sides and prepares an exhaustive correction proposal for review.

Scaling cocktail batches can introduce unit errors, unsuitable rounding, and hidden assumptions. This skill produces a reconciled ingredient sheet with explicit tolerances, manual actions, and optional container fit.

用户需要一种可靠的方式来查找可复用的 AI 技能。此技能通过 prompts.chat MCP 工具搜索、检索并安装 Agent Skills。

Unclear issue requests create rework, duplicates, and weak acceptance criteria. This skill produces reviewed GitHub issues with consistent structure and controlled publishing.

新的 Enact 用户需要一个易于检查的最小示例。此技能展示了一个面向 Claude、Codex 和 Claude Code 的仅提示词 hello-world 命令。

智能体经常需要为游戏、示例或随机测试值进行简单掷骰。此技能通过 Enact 运行一个 Rust 掷骰器，并返回每次掷骰结果及总数。

项目团队经常难以将规格说明转化为清晰的实施工作。此技能会把规格说明转换为分阶段任务，并包含依赖关系和验证步骤。

团队需要清晰的 Sprint 摘要，用于规划、评审和利益相关者更新。此技能可帮助将 Sprint 报告请求路由到专注的报告工作流。

自定义斜杠命令可能会变得不一致、权限过宽或难以测试。此技能通过模板、最小权限工具选择和 SlashCommand 验证来指导命令创建。

团队需要实用的功能创意，将用户价值、可行性和指标连接起来。此技能为 Web 和移动应用规划提供结构化头脑风暴指导。

当时间线、任务和依赖分散时，发布规划往往会失效。此技能可将项目上下文转化为 Sprint 日程、任务代码、里程碑和路线图视图。